triton-inference-server
added support to intel gpu in a custom build
Additional build flag --enable-intel-gpu which includes in the docker image required runtime drivers for Intel GPU Related to https://github.com/triton-inference-server/openvino_backend/pull/74/files
Don't we need to modify OpenVINO backend as well? I believe we were not installing openVINO GPU plugin. Are we now supporting both discrete and integrated GPUs in Triton OpenVINO backend?
Agree, looks like at least this place need to be updated https://github.com/triton-inference-server/openvino_backend/blob/main/CMakeLists.txt#L213 (not sure why custom plugins.xml is required?)
@tanmayv25 Related change in the openvino_backend is included in https://github.com/triton-inference-server/openvino_backend/pull/74/files Merge is pending your review for this PR. If you are ok with this approach, the first step would be merging the support in the backend.